---
title: "SNAPPerf: Software-Aware Tabular Foundation Model for Retraining-Free Performance Prediction of Configurable Systems"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00944v1"
permalink: "https://feed.astralor.com/items/itm_5b8b8ec97f5a17c091323a6e"
published: "2026-10-31T13:47:08.000Z"
score: 59
channel: "ai"
tags: ["AI Agent","RAG","SNAPPerf","Software-Aware Tabular Foundation","Model","Retraining-Free Performance Prediction","Configurable Systems Modern","Measuring"]
---

# SNAPPerf: Software-Aware Tabular Foundation Model for Retraining-Free Performance Prediction of Configurable Systems

## 速览

Modern software systems expose hundreds of configuration options whose combinations can substantially affect execution time, memory and energy usage. Measuring software performance resulting from a configuration set req…

## 关键点

- Modern software systems expose hundreds of configuration options whose combinations can substantially affect execution time, memory and energy usage.
- Measuring software performance resulting from a configuration set requires running a realistic workload.
- Since the configuration space grows exponentially, exhaustive benchmarking is infeasible.

## 全文

Modern software systems expose hundreds of configuration options whose combinations can substantially affect execution time, memory and energy usage. Measuring software performance resulting from a configuration set requires running a realistic workload. Since the configuration space grows exponentially, exhaustive benchmarking is infeasible. Prior work therefore trains models on a small set of measured configurations to predict the performance of the rest. Yet these models are specific to a particular software version, hardware platform, and workload, so changes require new measurements and retraining, and such changes are becoming more frequent with coding agents. We challenge this per-system training assumption with SNAPPERF (Software-aware, No-retraining, Adaptive Prediction), a sample-efficient tabular foundation model specialized for configurable software. SNAPPERF is pretrained once on synthetic data. Each new update only requires a few measured configurations as context to predict the rest without any per-system training or hyperparameter tuning. Across 39,866 configurations from 12 real-world systems, spanning 6 domains and 4 performance metrics, SNAPPERF reduces prediction error by 38% over the prior state of the art at the same measurement budget, and by 25% over the best general-purpose tabular foundation model. It matches the state of the art's accuracy with 54% fewer measurements on average. These results suggest that knowledge about software can be encoded in pretraining data rather than in per-system models, opening a new research direction in software-aware pretraining.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_5b8b8ec97f5a17c091323a6e